Hacker News new | past | comments | ask | show | jobs | submit login
Errors in the MMLU: The Deep Learning Benchmark Is Wrong Surprisingly Often (derenrich.medium.com)
2 points by brokensegue on Aug 23, 2023 | hide | past | favorite



Consider applying for YC's W25 batch! Applications are open till Nov 12.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: